DeepSeek V4 Flash API: pricing, base URL and quick setup

Specifications and pricing

Prices synced with platform billing (USD per 1M tokens).

Quick setup

curl https://a2agent.me/v1/chat/completions \
  -H "content-type: application/json" \
  -H "authorization: Bearer sk-your-a2agent-key" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Reply with OK"}]
  }'

Using it from a coding client

A sane default in Cline and Roo Code, where a session fires many small requests and the per-call rate compounds. Watch the output rate rather than the input one if your prompts are short and the answers run long.

• Run it in Cline
• Run it in Roo Code

How it compares within its family

Flash is the lower of the two DeepSeek V4 tiers sold here, and price is the whole gap. Context is 1M on both. The reasoning tag is on both. Flash lists at $0.14 per million input tokens against $0.435 for V4 Pro, and $0.28 output against $0.87. At that spread you can run a task three times on Flash for the price of one Pro call, which changes what is worth trying: sampling several answers and picking, or re-running a failed parse, stops being expensive. Where Flash stops being the right answer is a single high-stakes call nobody will check. There, paying Pro once beats paying Flash three times and still guessing which output to trust.

Other models on this platform

• DeepSeek V4 Pro1M

Questions